Narrow Results

VH-CATT cylindrical gear is a new transmission mechanism. In order to study the influence of design parameters and material strength degradation of the VH-CATT cylindrical gear on its transmission reliability. The Kriging surrogate model based on improved quantum particle swarm optimization (QPSO) algorithm was used to establish the limit state equation of contact stress for the VH-CATT cylindrical gear based on the stress-strength interference theory. The state equation of contact stress of the VH-CATT cylindrical gear was obtained with higher precision. Also, the strength degradation model with gamma distribution was established by using the P-S-N curve to estimate the parameters of the strength degradation model with gamma distribution. The reliability sensitivity of the VH-CATT cylindrical gear was analyzed by improved first order second moment method (AFOSM) based on the limit state equation of contact stress of the VH-CATT cylindrical gear, the reliability of gear considering strength degradation was studied by using the improved first order second moment method (AFOSM). The analysis results show that the failure rate decreases with the increase of pressure Angle, tooth width, modulus and tooth radius. The failure rate increases with increasing torque. Strength degradation has a certain influence on the reliability of gear and opinion. And the reliability of the gear is lower than that of the opinion, Strength degradation has a greater influence on the failure probability of gear, at the same time, the reliability of the gear pair decreases with the strength degradation. After 15000 hours of operation, the reliability of the gear pair is only 0.63155.

The author of this paper has conducted the experimental study and optimal computing for the condenser of automobile air conditioner. Especially studied and computed the properties of heat transfer and flow at the side of air when using louvered fin. Analyzed the influence of several combinations of fin's geometrical dimensions to heat transfer and pressure drop. Furthermore, designed a program to conduct optimal computing, and the computing results are basically consistent with experimental results.

In deep learning, convolutional neural networks (CNNs) are a class of artificial neural networks (ANNs), most commonly applied to analyze visual imagery. They are also known as Shift-Invariant or Space-Invariant Artificial Neural Networks (SIANNs), based on the shared-weight architecture of the convolution kernels or filters that slide along input features and provide translation-equivariant responses known as feature maps. Recently, various architectures for CNN based on FPGA platform have been proposed because it has the advantages of high performance and fast development cycle. However, some key issues including how to optimize the performance of CNN layers with different structures, high-performance heterogeneous accelerator design, and how to reduce the neural network framework integration overhead need to be improved. To overcome and improve these problems, we propose dynamic cycle pipeline tiling, data layout optimization, and a pipelined software and hardware (SW–HW)-integrated architecture with flexibility and integration. Some benchmarks have been tested and implemented on the FPGA board for the proposed architecture. The proposed dynamic tiling and data layout transformation improved by 2.3 times in the performance. Moreover, with two-level pipelining, we achieve up to five times speedup and the proposed system is 3.8 times more energy-efficient than the GPU.

Random forest is an ensemble classification algorithm. It performs well when most predictive variables are noisy and can be used when the number of variables is much larger than the number of observations. The use of bootstrap samples and restricted subsets of attributes makes it more powerful than simple ensembles of trees. The main advantage of a random forest classifier is its explanatory power: it measures variable importance or impact of each factor on a predicted class label. These characteristics make the algorithm ideal for microarray data. It was shown to build models with high accuracy when tested on high-dimensional microarray datasets. Current implementations of random forest in the machine learning and statistics community, however, limit its usability for mining over large datasets, as they require that the entire dataset remains permanently in memory. We propose a new framework, an optimized implementation of a random forest classifier, which addresses specific properties of microarray data, takes computational complexity of a decision tree algorithm into consideration, and shows excellent computing performance while preserving predictive accuracy. The implementation is based on reducing overlapping computations and eliminating dependency on the size of main memory. The implementation's excellent computational performance makes the algorithm useful for interactive data analyses and data mining.

When the risk control requirements incur significant increases in cost for overhauls, it's a necessity to update the current system to achieve risk control objectives. This article combines overhaul and system update together and considers a combinatorial optimization problem. A combinatorial optimization model is then established. The objective of the model is to find the appropriate time for system update as well as to optimize overhaul cycles for new and old equipments. Finally, the Monte Carlo method is used to simulate the model. Simulation results show that the combinatorial optimization model is effective.

On the basis of the current database system research, according to the Oracle database system, in this paper a database optimization program is presented and implemented. Experimental results show that: the database optimization program can improve the disposing performance of the database and greatly accelerate the pace of its inquiries.

In order to optimize high-order cumulant blind equalization algorithm, in this paper we propose an improved algorithm which can optimize the SW criterion with genetic algorithm and improve the algorithm performance with the global and fast convergence of genetic algorithm. Computer simulation results demonstrate that the improved algorithm has good convergence performance and error symbol resistance performance.